提取chm中的html,探讨一个从chm文件中提取自己想要的信息与数据的算法。我先说...

该楼层疑似违规已被系统折叠 隐藏此楼查看此楼

如下面这个，就是生成htm文件的

========

第一步:下载chm4j.jar

第二步:新建java工程,建一个解析ParseChm类,建一个解析测试类,类似:

ParseChm类:

//下面的包,请导入chm4j.jar,并且把chm4j.dll拷贝到jre的lib目录内,linux或mac请拷贝libchm4j.so即//可,因为chm4j.jar依赖于c++

packagecn.lswe.baseframe.utils;

importjava.io.File;

importjava.io.FileOutputStream;importjava.io.IOException;importjava.io.InputStream;importjava.io.OutputStream;

importorg.chm4j.*;

importcn.lswe.baseframe.validator.Conf;

publicclassParseChm{

publicstaticvoidmain(String...args){

try{

ChmFilecFile=newChmFile(Conf.ChmSOurce);Stringdir=Conf.dir;

ChmEntry.Attributeattributes=ChmEntry.Attribute.ALL;ChmEntry[]entries=cFile.entries(attributes);

for(ChmEntryentry:entries){listChmEntry(dir,entry,attributes);

}

}catch(IOExceptionex){

System.out.println("Error:"+ex.getMessage());

}

}

/**

*ExtractsrecursivelythesubentriesofthespecifiedChmEntryintothe

*specifiedoutputdirectoryaccordingtothespecifiedattributes.

*@paramoutputTheoutputdirectory.

*@paramentry

*@paramattributes

*@throwsjava.io.IOExceptionIfanI/Oerroroccurs.

*/

privatestaticvoidlistChmEntry(Stringoutput,ChmEntryentry,ChmEntry.Attributeattributes)throwsIOException{

printEntry(entry);

Stringer=GuidHelper.CreateGuid().toString();Filedest=newFile(output,entry.getPath());

if(entry.hasAttribute(ChmEntry.Attribute.DIRECTORY)){if(!dest.isDirectory()){

if(!dest.mkdirs()){

thrownewIOException("failedtocreatedirectory:"+dest);

}

}

for(ChmEntrye:entry.entries(attributes)){listChmEntry(output,e,attributes);

}

}else{

InputStreamin=null;OutputStreamout=null;try{

in=entry.getInputStream();

out=newFileOutputStream(dest);intbufferSize=1024;

byte[]data=newbyte[bufferSize];intnbRead;